{"id":"W4412852478","doi":"10.1007/978-3-031-96628-6_3","title":"PathTTT: Test-Time Training with Meta-auxiliary Learning for Pathology Image Classification","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Contextual image classification; Test (biology); Pattern recognition (psychology); Image (mathematics); Training (meteorology); Machine learning; Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00162316,0.002067183,0.001430553,0.001062911,0.0006835414,0.001397828,0.004580267,0.002831136,0.01490951],"category_scores_gemma":[0.004166272,0.001172533,0.001806115,0.001298686,0.0007979395,0.002745629,0.003212576,0.003525212,0.008880878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008514358,"about_ca_system_score_gemma":0.001987109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005373886,"about_ca_topic_score_gemma":0.008874371,"domain_scores_codex":[0.9989238,0.0002171489,0.00005511469,0.0004361438,0.0002091292,0.0001586565],"domain_scores_gemma":[0.9982338,0.0007751427,0.0000575352,0.000563239,0.0002690993,0.0001012713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007272082,0.0002919431,0.001514253,0.000180579,0.0002066182,0.0001434869,0.00007287087,0.05255747,0.009943735,0.002048319,0.04074518,0.8915684],"study_design_scores_gemma":[0.0001081565,0.0002467583,0.0005541317,0.00003280848,0.00007378789,0.0001368756,0.00003676345,0.9722121,0.01105951,0.008051246,0.007463167,0.00002466106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02097637,0.001106247,0.8897299,0.0003739334,0.0004688197,0.0002939755,0.002131935,0.08038824,0.004530688],"genre_scores_gemma":[0.247319,0.0003555189,0.7199452,0.0006407676,0.0002052743,0.0006778403,0.01016079,0.003831886,0.01686357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01490951,"threshold_uncertainty_score":0.04987729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0358980018059981,"score_gpt":0.2631283829052097,"score_spread":0.2272303810992116,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}